cs.CVNov 8, 2026

Rethinking Geometric Depth in Monocular 3D Object Detection: A Projection-Consistent Reformulation

Authors: Zhihao Zhang, Abhinav Kumar, Huaizhi Qu, Tianlong Chen, Xiaoming Liu

Organizations: Michigan State University · University of North Carolina at Chapel Hill

Abstract

Monocular 3D detection (Mono3D) hinges on recovering depth from a single image, for which the geometric formulation z≈f⋅H/h2Dz \approx f \cdot H / h_{2D} is widely adopted due to its simplicity and direct grounding in projective geometry. We show that this formulation harbors a systematic, projection-induced bias: substituting the 2D bounding-box height h2Dh_{2D} recovers the depth of an object's visible front surface rather than its center, causing size-dependent underestimation that persists even under ground-truth inputs. We address this front-surface bias with MonoPCA, a unified framework built on a projection-consistent reformulation. At its core, PCDepth retains the measurable h2Dh_{2D} and closes the gap to center depth through an orientation- and size-aware correction derived from perspective geometry, eliminating the bias without introducing ill-posed regression targets. Because PCDepth couples depth to predicted object size and orientation, attribute perception becomes essential. We therefore introduce GeoAlign, a teacher-student framework that transfers geometric representations from Vision Foundation Models into a lightweight student, strengthening attribute perception at no inference cost. Across four challenging benchmarks, MonoPCA achieves SoTA performance, including a +1.44% AP3D_{3D} gain on the KITTI leaderboard and +2.80% on Omni3DOUT_{OUT}. Code is available at https://github.com/alanzhangcs/MonoPCA.

Figures & tables

Explore similar work

CardsList
  1. MonoPRIO: Adaptive Prior Conditioning for Unified Monocular 3D Object Detection

    May 14, 2026Leon Davies, Qinggang Meng, Mohamad Saada +23D Object DetectionMonocular 3D Object Detection

  2. LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection

    Dec 5, 2025Johannes Meier, Jonathan Michel, Oussema Dhaouadi +7Efficient Object DetectionReal-Time Object Detection